forked from mongodb/mongo-go-driver
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbson_corpus_spec_test.go
446 lines (375 loc) · 13.3 KB
/
bson_corpus_spec_test.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
// Copyright (C) MongoDB, Inc. 2017-present.
//
// Licensed under the Apache License, Version 2.0 (the "License"); you may
// not use this file except in compliance with the License. You may obtain
// a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
package bson
import (
"encoding/hex"
"encoding/json"
"fmt"
"io/ioutil"
"math"
"path"
"strconv"
"strings"
"testing"
"unicode"
"unicode/utf8"
"github.com/google/go-cmp/cmp"
"github.com/stretchr/testify/require"
"github.com/tidwall/pretty"
"go.mongodb.org/mongo-driver/bson/primitive"
"go.mongodb.org/mongo-driver/internal/testutil/assert"
)
type testCase struct {
Description string `json:"description"`
BsonType string `json:"bson_type"`
TestKey *string `json:"test_key"`
Valid []validityTestCase `json:"valid"`
DecodeErrors []decodeErrorTestCase `json:"decodeErrors"`
ParseErrors []parseErrorTestCase `json:"parseErrors"`
Deprecated *bool `json:"deprecated"`
}
type validityTestCase struct {
Description string `json:"description"`
CanonicalBson string `json:"canonical_bson"`
CanonicalExtJSON string `json:"canonical_extjson"`
RelaxedExtJSON *string `json:"relaxed_extjson"`
DegenerateBSON *string `json:"degenerate_bson"`
DegenerateExtJSON *string `json:"degenerate_extjson"`
ConvertedBSON *string `json:"converted_bson"`
ConvertedExtJSON *string `json:"converted_extjson"`
Lossy *bool `json:"lossy"`
}
type decodeErrorTestCase struct {
Description string `json:"description"`
Bson string `json:"bson"`
}
type parseErrorTestCase struct {
Description string `json:"description"`
String string `json:"string"`
}
const dataDir = "../data/bson-corpus/"
func findJSONFilesInDir(t *testing.T, dir string) []string {
files := make([]string, 0)
entries, err := ioutil.ReadDir(dir)
require.NoError(t, err)
for _, entry := range entries {
if entry.IsDir() || path.Ext(entry.Name()) != ".json" {
continue
}
files = append(files, entry.Name())
}
return files
}
func needsEscapedUnicode(bsonType string) bool {
return bsonType == "0x02" || bsonType == "0x0D" || bsonType == "0x0E" || bsonType == "0x0F"
}
func unescapeUnicode(s, bsonType string) string {
if !needsEscapedUnicode(bsonType) {
return s
}
newS := ""
for i := 0; i < len(s); i++ {
c := s[i]
switch c {
case '\\':
switch s[i+1] {
case 'u':
us := s[i : i+6]
u, err := strconv.Unquote(strings.Replace(strconv.Quote(us), `\\u`, `\u`, 1))
if err != nil {
return ""
}
for _, r := range u {
if r < ' ' {
newS += fmt.Sprintf(`\u%04x`, r)
} else {
newS += string(r)
}
}
i += 5
default:
newS += string(c)
}
default:
if c > unicode.MaxASCII {
r, size := utf8.DecodeRune([]byte(s[i:]))
newS += string(r)
i += size - 1
} else {
newS += string(c)
}
}
}
return newS
}
func formatDouble(f float64) string {
var s string
if math.IsInf(f, 1) {
s = "Infinity"
} else if math.IsInf(f, -1) {
s = "-Infinity"
} else if math.IsNaN(f) {
s = "NaN"
} else {
// Print exactly one decimalType place for integers; otherwise, print as many are necessary to
// perfectly represent it.
s = strconv.FormatFloat(f, 'G', -1, 64)
if !strings.ContainsRune(s, 'E') && !strings.ContainsRune(s, '.') {
s += ".0"
}
}
return s
}
func normalizeCanonicalDouble(t *testing.T, key string, cEJ string) string {
// Unmarshal string into map
cEJMap := make(map[string]map[string]string)
err := json.Unmarshal([]byte(cEJ), &cEJMap)
require.NoError(t, err)
// Parse the float contained by the map.
expectedString := cEJMap[key]["$numberDouble"]
expectedFloat, err := strconv.ParseFloat(expectedString, 64)
require.NoError(t, err)
// Normalize the string
return fmt.Sprintf(`{"%s":{"$numberDouble":"%s"}}`, key, formatDouble(expectedFloat))
}
func normalizeRelaxedDouble(t *testing.T, key string, rEJ string) string {
// Unmarshal string into map
rEJMap := make(map[string]float64)
err := json.Unmarshal([]byte(rEJ), &rEJMap)
if err != nil {
return normalizeCanonicalDouble(t, key, rEJ)
}
// Parse the float contained by the map.
expectedFloat := rEJMap[key]
// Normalize the string
return fmt.Sprintf(`{"%s":%s}`, key, formatDouble(expectedFloat))
}
// bsonToNative decodes the BSON bytes (b) into a native Document
func bsonToNative(t *testing.T, b []byte, bType, testDesc string) D {
var doc D
err := Unmarshal(b, &doc)
expectNoError(t, err, fmt.Sprintf("%s: decoding %s BSON", testDesc, bType))
return doc
}
// nativeToBSON encodes the native Document (doc) into canonical BSON and compares it to the expected
// canonical BSON (cB)
func nativeToBSON(t *testing.T, cB []byte, doc D, testDesc, bType, docSrcDesc string) {
actual, err := Marshal(doc)
expectNoError(t, err, fmt.Sprintf("%s: encoding %s BSON", testDesc, bType))
if diff := cmp.Diff(cB, actual); diff != "" {
t.Errorf("%s: 'native_to_bson(%s) = cB' failed (-want, +got):\n-%v\n+%v\n",
testDesc, docSrcDesc, cB, actual)
t.FailNow()
}
}
// jsonToNative decodes the extended JSON string (ej) into a native Document
func jsonToNative(t *testing.T, ej, ejType, testDesc string) D {
var doc D
err := UnmarshalExtJSON([]byte(ej), ejType != "relaxed", &doc)
expectNoError(t, err, fmt.Sprintf("%s: decoding %s extended JSON", testDesc, ejType))
return doc
}
// nativeToJSON encodes the native Document (doc) into an extended JSON string
func nativeToJSON(t *testing.T, ej string, doc D, testDesc, ejType, ejShortName, docSrcDesc string) {
actualEJ, err := MarshalExtJSON(doc, ejType != "relaxed", true)
expectNoError(t, err, fmt.Sprintf("%s: encoding %s extended JSON", testDesc, ejType))
if diff := cmp.Diff(ej, string(actualEJ)); diff != "" {
t.Errorf("%s: 'native_to_%s_extended_json(%s) = %s' failed (-want, +got):\n%s\n",
testDesc, ejType, docSrcDesc, ejShortName, diff)
t.FailNow()
}
}
func runTest(t *testing.T, file string) {
filepath := path.Join(dataDir, file)
content, err := ioutil.ReadFile(filepath)
require.NoError(t, err)
// Remove ".json" from filename.
file = file[:len(file)-5]
testName := "bson_corpus--" + file
t.Run(testName, func(t *testing.T) {
var test testCase
require.NoError(t, json.Unmarshal(content, &test))
t.Run("valid", func(t *testing.T) {
for _, v := range test.Valid {
t.Run(v.Description, func(t *testing.T) {
// get canonical BSON
cB, err := hex.DecodeString(v.CanonicalBson)
expectNoError(t, err, fmt.Sprintf("%s: reading canonical BSON", v.Description))
// get canonical extended JSON
cEJ := unescapeUnicode(string(pretty.Ugly([]byte(v.CanonicalExtJSON))), test.BsonType)
if test.BsonType == "0x01" {
cEJ = normalizeCanonicalDouble(t, *test.TestKey, cEJ)
}
/*** canonical BSON round-trip tests ***/
doc := bsonToNative(t, cB, "canonical", v.Description)
// native_to_bson(bson_to_native(cB)) = cB
nativeToBSON(t, cB, doc, v.Description, "canonical", "bson_to_native(cB)")
// native_to_canonical_extended_json(bson_to_native(cB)) = cEJ
nativeToJSON(t, cEJ, doc, v.Description, "canonical", "cEJ", "bson_to_native(cB)")
// native_to_relaxed_extended_json(bson_to_native(cB)) = rEJ (if rEJ exists)
if v.RelaxedExtJSON != nil {
rEJ := unescapeUnicode(string(pretty.Ugly([]byte(*v.RelaxedExtJSON))), test.BsonType)
if test.BsonType == "0x01" {
rEJ = normalizeRelaxedDouble(t, *test.TestKey, rEJ)
}
nativeToJSON(t, rEJ, doc, v.Description, "relaxed", "rEJ", "bson_to_native(cB)")
/*** relaxed extended JSON round-trip tests (if exists) ***/
doc = jsonToNative(t, rEJ, "relaxed", v.Description)
// native_to_relaxed_extended_json(json_to_native(rEJ)) = rEJ
nativeToJSON(t, rEJ, doc, v.Description, "relaxed", "eJR", "json_to_native(rEJ)")
}
/*** canonical extended JSON round-trip tests ***/
doc = jsonToNative(t, cEJ, "canonical", v.Description)
// native_to_canonical_extended_json(json_to_native(cEJ)) = cEJ
nativeToJSON(t, cEJ, doc, v.Description, "canonical", "cEJ", "json_to_native(cEJ)")
// native_to_bson(json_to_native(cEJ)) = cb (unless lossy)
if v.Lossy == nil || !*v.Lossy {
nativeToBSON(t, cB, doc, v.Description, "canonical", "json_to_native(cEJ)")
}
/*** degenerate BSON round-trip tests (if exists) ***/
if v.DegenerateBSON != nil {
dB, err := hex.DecodeString(*v.DegenerateBSON)
expectNoError(t, err, fmt.Sprintf("%s: reading degenerate BSON", v.Description))
doc = bsonToNative(t, dB, "degenerate", v.Description)
// native_to_bson(bson_to_native(dB)) = cB
nativeToBSON(t, cB, doc, v.Description, "degenerate", "bson_to_native(dB)")
}
/*** degenerate JSON round-trip tests (if exists) ***/
if v.DegenerateExtJSON != nil {
dEJ := unescapeUnicode(string(pretty.Ugly([]byte(*v.DegenerateExtJSON))), test.BsonType)
if test.BsonType == "0x01" {
dEJ = normalizeCanonicalDouble(t, *test.TestKey, dEJ)
}
doc = jsonToNative(t, dEJ, "degenerate canonical", v.Description)
// native_to_canonical_extended_json(json_to_native(dEJ)) = cEJ
nativeToJSON(t, cEJ, doc, v.Description, "degenerate canonical", "cEJ", "json_to_native(dEJ)")
// native_to_bson(json_to_native(dEJ)) = cB (unless lossy)
if v.Lossy == nil || !*v.Lossy {
nativeToBSON(t, cB, doc, v.Description, "canonical", "json_to_native(dEJ)")
}
}
})
}
})
t.Run("decode error", func(t *testing.T) {
for _, d := range test.DecodeErrors {
t.Run(d.Description, func(t *testing.T) {
b, err := hex.DecodeString(d.Bson)
expectNoError(t, err, d.Description)
var doc D
err = Unmarshal(b, &doc)
// The driver unmarshals invalid UTF-8 strings without error. Loop over the unmarshalled elements
// and assert that there was no error if any of the string or DBPointer values contain invalid UTF-8
// characters.
for _, elem := range doc {
str, ok := elem.Value.(string)
invalidString := ok && !utf8.ValidString(str)
dbPtr, ok := elem.Value.(primitive.DBPointer)
invalidDBPtr := ok && !utf8.ValidString(dbPtr.DB)
if invalidString || invalidDBPtr {
expectNoError(t, err, d.Description)
return
}
}
expectError(t, err, fmt.Sprintf("%s: expected decode error", d.Description))
})
}
})
t.Run("parse error", func(t *testing.T) {
for _, p := range test.ParseErrors {
t.Run(p.Description, func(t *testing.T) {
s := unescapeUnicode(p.String, test.BsonType)
if test.BsonType == "0x13" {
s = fmt.Sprintf(`{"decimal128": {"$numberDecimal": "%s"}}`, s)
}
switch test.BsonType {
case "0x00", "0x05", "0x13":
var doc D
err := UnmarshalExtJSON([]byte(s), true, &doc)
// Null bytes are validated when marshaling to BSON
if strings.Contains(p.Description, "Null") {
_, err = Marshal(doc)
}
expectError(t, err, fmt.Sprintf("%s: expected parse error", p.Description))
default:
t.Errorf("Update test to check for parse errors for type %s", test.BsonType)
t.Fail()
}
})
}
})
})
}
func Test_BsonCorpus(t *testing.T) {
for _, file := range findJSONFilesInDir(t, dataDir) {
runTest(t, file)
}
}
func expectNoError(t *testing.T, err error, desc string) {
if err != nil {
t.Helper()
t.Errorf("%s: Unepexted error: %v", desc, err)
t.FailNow()
}
}
func expectError(t *testing.T, err error, desc string) {
if err == nil {
t.Helper()
t.Errorf("%s: Expected error", desc)
t.FailNow()
}
}
func TestRelaxedUUIDValidation(t *testing.T) {
testCases := []struct {
description string
canonicalExtJSON string
degenerateExtJSON string
expectedErr string
}{
{
"valid uuid",
"{\"x\" : { \"$binary\" : {\"base64\" : \"c//SZESzTGmQ6OfR38A11A==\", \"subType\" : \"04\"}}}",
"{\"x\" : { \"$uuid\" : \"73ffd264-44b3-4c69-90e8-e7d1dfc035d4\"}}",
"",
},
{
"invalid uuid--no hyphens",
"",
"{\"x\" : { \"$uuid\" : \"73ffd26444b34c6990e8e7d1dfc035d4\"}}",
"$uuid value does not follow RFC 4122 format regarding length and hyphens",
},
{
"invalid uuid--trailing hyphens",
"",
"{\"x\" : { \"$uuid\" : \"73ffd264-44b3-4c69-90e8-e7d1dfc035--\"}}",
"$uuid value does not follow RFC 4122 format regarding length and hyphens",
},
{
"invalid uuid--malformed hex",
"",
"{\"x\" : { \"$uuid\" : \"q3@fd26l-44b3-4c69-90e8-e7d1dfc035d4\"}}",
"$uuid value does not follow RFC 4122 format regarding hex bytes: encoding/hex: invalid byte: U+0071 'q'",
},
}
for _, tc := range testCases {
t.Run(tc.description, func(t *testing.T) {
// get canonical extended JSON
cEJ := unescapeUnicode(string(pretty.Ugly([]byte(tc.canonicalExtJSON))), "0x05")
// get degenerate extended JSON
dEJ := unescapeUnicode(string(pretty.Ugly([]byte(tc.degenerateExtJSON))), "0x05")
// convert dEJ to native doc
var doc D
err := UnmarshalExtJSON([]byte(dEJ), true, &doc)
if tc.expectedErr != "" {
assert.Equal(t, tc.expectedErr, err.Error(), "expected error %v, got %v", tc.expectedErr, err)
} else {
assert.Nil(t, err, "expected no error, got error: %v", err)
// Marshal doc into extended JSON and compare with cEJ
nativeToJSON(t, cEJ, doc, tc.description, "degenerate canonical", "cEJ", "json_to_native(dEJ)")
}
})
}
}